Detailed python notes & code for lectures and exercises of Andrej Karpathy's course "Neural Networks: Zero to Hero." The course is focused on building neural networks from scratch.

Implementation of Karpathy's micrograd in Mojo 🔥

Building Andrej Kapathy's micrograd from scratch

yet another scalar autograd engine - featuring complex numbers and fixed DAG

A C++ implementation of the scalar-valued autograd engine micrograd

📖 A self-contained course to learn the basics of neural networks: from backprop to GPT! 🌻

Micrograd but in Rust

C implementation of micrograd

A rust implementation of Andrej Karpathy's Micrograd

The easiest way to build Neural Networks in C# within Unity. The open-source AI project implements a scalar-valued autograd engine so you don't have to deal with backpropagation, and a Neural Network library. You can use it outside of Unity as well.

A Deep Neural network from scratch in Java

micrograd, but in C++ and better

A porting of Karpathy's Micrograd to JS

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

Torch-like deep learning framework for Javascript

Small scalar autograd engine, inspired from Karpathy's micrograd, with some additional features, such as more activation functions, optimizers and loss criterions.

🎓 super small and cute neural net engine, using only numpy

small (and partial) autograd engine inspired from Karpathy's micrograd and PyTorch, written in Zig

A simple vector valued autograd engine aimed to be between micrograd and tinygrad with a nn library.

A port of karpathy/micrograd from Python to C#. The project itself is a tiny scalar-valued autograd engine and basic neural network implementation on top of it.